Article Per Year (5 Year)
p-Index From 2021 - 2026
0.702
P-Index
This Author published in this journals
All Journal SAGA: Journal of Technology and Information Systems Journal of Intelligent Systems and Information Technology The ASEAN Journal of Military and Preventive Medicine Mandailing Journal of Education and Sciences
Muhammad Sobri Maulana
RSAU Esnawan Antariksa Jakarta
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering Library & Information Science

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
AI-DRIVEN VOCABULARY PERSONALIZATION: FILLING THE GAP IN TRANSPARENCY AND LEARNER TRUST IN ADAPTIVE RECOMMENDER SYSTEMS FOR LANGUAGE LEARNING Muhammad Sobri Maulana; Arditya Prayogi; Dwitia Pratiwi
Mandailing Journal of Education and Sciences Vol. 1 No. 2 (2026): Vol. 1 No. 2, Juli 2026
Publisher : PT Mandailing Publisher Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66698/mjoes.v1i2.9

Abstract

AI-driven vocabulary recommender systems can personalize vocabulary practice by using learner data such as prior performance, error patterns, goals, and review schedules. However, many systems remain opaque because they recommend words without explaining why the items are selected or how learners can adjust the recommendation process. This conceptual article examines transparency as a key design issue in technology-enhanced language learning and synthesizes literature on explainable AI, trust in automation, technology acceptance, and self-regulated learning. The results of the synthesis show that transparent vocabulary personalization is most likely to support learning when it strengthens three mechanisms: perceived control, calibrated trust, and sustained adoption. The analysis also indicates that the most appropriate design is not excessive technical disclosure, but concise explanations, on-demand details, and learner controls that allow users to correct or adjust recommendations. These findings suggest that trustworthy vocabulary recommenders should combine pedagogically meaningful explanations with learner agency so that adaptive systems support, rather than replace, self-regulated learning.
RadOnco-Priority: Machine Learning Decision Support for Radiotherapy Queue Prioritization Using Real-World Retrospective Radiotherapy Referral Data Muhammad Sobri Maulana; Dwitia Pratiwi; Arditya Prayogi
SAGA: Journal of Technology and Information System Vol. 4 No. 2 (2026): May 2026
Publisher : CV. Media Digital Publikasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58905/saga.v4i2.685

Abstract

Radiotherapy queues are often managed by referral date and manual clinician judgment, although limited linear accelerator capacity requires prioritization that is clinically transparent, operationally auditable, and fair. This study evaluates RadOnco-Priority, a machine learning-enabled decision support framework for radiotherapy queue prioritization, using a de-identified real-world retrospective dataset of 240 radiotherapy referral records rather than simulated or synthetic patient records. The system combines a literature-informed rule-based urgency score with supervised machine learning models to identify patients requiring accelerated booking. Accelerated booking need was defined a priori as an operational triage label reflecting clinician-documented priority, urgent symptoms, time-sensitive tumor-site and treatment-intent combinations, accumulated referral delay, and planning complexity. Logistic regression, random forest, and gradient boosting were trained to predict accelerated booking need, while a capacity-aware scheduling simulation evaluated waiting-time redistribution. To address potential circularity, additional ablation analyses were performed with the aggregate urgency score removed from the predictors. In the held-out test set, logistic regression achieved the highest discrimination in the full-feature model (AUC 0.91), with sensitivity-oriented classification favoring reduced false negatives. Performance remained acceptable after removing the aggregate urgency score, indicating that the model did not rely solely on the pre-specified scoring logic. The scheduling simulation reduced median waiting time in the high-priority group and decreased the proportion of high-priority patients waiting more than 28 days. These findings support RadOnco-Priority as an interpretable, human-governed information-system framework for radiotherapy queue management. Prospective multicenter validation, fairness monitoring, and local ethics approval remain required before routine implementation.
Vaccination programs and infectious disease burden among military personnel: a systematic review with pathogen-specific quantitative synthesis Muhammad Sobri Maulana; Dwitia Pratiwi; Arditya Prayogi
The ASEAN Journal of Military and Preventive Medicine Vol. 3 No. 2 (2026): July
Publisher : Perkumpulan Kedokteran Militer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47353/ajmpm.v3i2.17

Abstract

Introduction: Military personnel are highly exposed to vaccine-preventable infections because of close living conditions, rapid mobilization, deployment to endemic areas, and intense training schedules. This systematic review and meta-analysis evaluated whether vaccination programs reduce infectious disease burden among military personnel. Methods: PubMed/MEDLINE, Embase, Cochrane Library, ProQuest, and Scopus were searched from database inception to 16 May 2026 for comparative studies of vaccination programs in military populations. Eligible outcomes were laboratory-confirmed infection, clinical disease, acute respiratory illness, meningococcal disease, or program-defined infectious disease burden. Random-effects meta-analysis was performed using log risk ratios. Results: Sixteen studies were included in the qualitative synthesis and 13 contributed quantitative data. Across adenovirus, meningococcal, influenza, and COVID-19 vaccination programs, the pooled risk ratio was 0.19 (95% confidence interval 0.11-0.32), corresponding to an approximate 81% reduction in infectious disease burden. Subgroup effects were strongest for adenovirus and meningococcal vaccination programs and more moderate for influenza vaccination. Discussion: The findings support vaccination as a high-impact readiness intervention in military settings, especially for pathogens amplified by recruit training environments. Certainty was limited by heterogeneity, pre-post designs, historical evidence, and inconsistent reporting of denominators. Conclusion: Vaccination programs substantially reduce infectious disease burden among military personnel. Future research should use prospective surveillance, standardized case definitions, pathogen-specific laboratory confirmation, and transparent reporting of denominators and person-time.
MolecuTrace: Development of a Web-Based Molecular Oncology Dashboard for Integrating Sample Metadata, SNV Profiles, and Cancer Stage Classification Muhammad Sobri Maulana; Dwitia Pratiwi; Arditya Prayogi
Journal of Intelligent Systems and Information Technology Vol. 3 No. 2 (2026): July
Publisher : Apik Cahaya Ilmu

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61971/jisit.v3i2.307

Abstract

Cancer molecular profiling produces heterogeneous data streams, including patient metadata, biological sample information, single-nucleotide variant (SNV) records, variant annotations, and cancer stage labels. In many hospital and laboratory settings, these elements remain fragmented across spreadsheets, variant call files, and narrative reports, limiting the ability of clinicians and researchers to obtain rapid sample-to-insight interpretation. This study presents MolecuTrace, a web-based molecular oncology dashboard designed to integrate sample metadata, SNV profiles, and cancer stage classification into a structured decision-support prototype. A design science research approach was used to define requirements, model the database, implement an analytics workflow, and evaluate the prototype with a simulated demonstration dataset of 120 oncology samples and 253 SNV records. The system consists of a sample registry, SNV import and validation module, annotation layer, risk-scoring engine, dashboard visualization, and exportable report interface. The demonstration dataset showed a mean age of 53.9 years, 44.2% metastatic cases, and TP53 as the most frequently observed altered gene. MolecuTrace generated summary indicators for cancer type distribution, sample source composition, top altered genes, metastatic status, and molecular risk classes. The proposed prototype contributes an interoperable, auditable, and clinically readable model for transforming molecular oncology data into actionable visual summaries. Although the current evaluation uses simulated data and requires external clinical validation, the framework demonstrates how a lightweight information system can support precision oncology workflows in resource-constrained healthcare settings.
Co-Authors Arditya Prayogi Dwitia Pratiwi